def build_made(
batch_x: Tensor = None,
batch_y: Tensor = None,
z_score_x: bool = True,
z_score_y: bool = True,
hidden_features: int = 50,
num_blocks: int = 5,
num_mixture_components: int = 10,
embedding_net: nn.Module = nn.Identity(),
) -> nn.Module:
"""Builds MADE p(x|y).
Args:
batch_x: Batch of xs, used to infer dimensionality and (optional) z-scoring.
batch_y: Batch of ys, used to infer dimensionality and (optional) z-scoring.
z_score_x: Whether to z-score xs passing into the network.
z_score_y: Whether to z-score ys passing into the network.
hidden_features: Number of hidden features.
num_blocks: Number of MADE blocks.
num_mixture_components: Number of mixture components.
embedding_net: Optional embedding network for y.
Returns:
Neural network.
"""
x_numel = batch_x[0].numel()
y_numel = batch_y[0].numel()
if x_numel == 1:
warn(
f"In one-dimensional output space, this flow is limited to Gaussians"
)
transform = transforms.IdentityTransform()
if z_score_x:
transform_zx = standardizing_transform(batch_x)
transform = transforms.CompositeTransform([transform_zx, transform])
if z_score_y:
embedding_net = nn.Sequential(standardizing_net(batch_y),
embedding_net)
distribution = distributions_.MADEMoG(
features=x_numel,
hidden_features=hidden_features,
context_features=y_numel,
num_blocks=num_blocks,
num_mixture_components=num_mixture_components,
use_residual_blocks=True,
random_mask=False,
activation=relu,
dropout_probability=0.0,
use_batch_norm=False,
custom_initialization=True,
)
neural_net = flows.Flow(transform, distribution, embedding_net)
return neural_net
def posterior_nn(
model: str,
prior: torch.distributions.Distribution,
context: torch.Tensor,
embedding: Optional[torch.nn.Module] = None,
hidden_features: int = 50,
mdn_num_components: int = 20,
made_num_mixture_components: int = 10,
made_num_blocks: int = 4,
flow_num_transforms: int = 5,
) -> torch.nn.Module:
"""Neural posterior density estimator
Args:
model: Model, one of maf / mdn / made / nsf
prior: Prior distribution
context: Observation
embedding: Embedding network
hidden_features: For all, number of hidden features
mdn_num_components: For MDNs only, number of components
made_num_mixture_components: For MADEs only, number of mixture components
made_num_blocks: For MADEs only, number of blocks
flow_num_transforms: For flows only, number of transforms
Returns:
Neural network
"""
mean, std = (prior.mean, prior.stddev)
standardizing_transform = transforms.AffineTransform(
shift=-mean / std, scale=1 / std
)
parameter_dim = prior.sample([1]).shape[1]
context = utils.torchutils.atleast_2d(context)
observation_dim = torch.tensor([context.shape[1:]])
if model == "mdn":
neural_net = MultivariateGaussianMDN(
features=parameter_dim,
context_features=observation_dim,
hidden_features=hidden_features,
hidden_net=nn.Sequential(
nn.Linear(observation_dim, hidden_features),
nn.ReLU(),
nn.Dropout(p=0.0),
nn.Linear(hidden_features, hidden_features),
nn.ReLU(),
nn.Linear(hidden_features, hidden_features),
nn.ReLU(),
),
num_components=mdn_num_components,
custom_initialization=True,
)
elif model == "made":
transform = standardizing_transform
distribution = distributions_.MADEMoG(
features=parameter_dim,
hidden_features=hidden_features,
context_features=observation_dim,
num_blocks=made_num_blocks,
num_mixture_components=made_num_mixture_components,
use_residual_blocks=True,
random_mask=False,
activation=torch.relu,
dropout_probability=0.0,
use_batch_norm=False,
custom_initialization=True,
)
neural_net = flows.Flow(transform, distribution, embedding)
elif model == "maf":
transform = transforms.CompositeTransform(
[
transforms.CompositeTransform(
[
transforms.MaskedAffineAutoregressiveTransform(
features=parameter_dim,
hidden_features=hidden_features,
context_features=observation_dim,
num_blocks=2,
use_residual_blocks=False,
random_mask=False,
activation=torch.tanh,
dropout_probability=0.0,
use_batch_norm=True,
),
transforms.RandomPermutation(features=parameter_dim),
]
)
for _ in range(flow_num_transforms)
]
)
transform = transforms.CompositeTransform([standardizing_transform, transform,])
distribution = distributions_.StandardNormal((parameter_dim,))
neural_net = flows.Flow(transform, distribution, embedding)
elif model == "nsf":
transform = transforms.CompositeTransform(
[
transforms.CompositeTransform(
[
transforms.PiecewiseRationalQuadraticCouplingTransform(
mask=create_alternating_binary_mask(
features=parameter_dim, even=(i % 2 == 0)
),
transform_net_create_fn=lambda in_features, out_features: nets.ResidualNet(
in_features=in_features,
out_features=out_features,
hidden_features=hidden_features,
context_features=observation_dim,
num_blocks=2,
activation=torch.relu,
dropout_probability=0.0,
use_batch_norm=False,
),
num_bins=10,
tails="linear",
tail_bound=3.0,
apply_unconditional_transform=False,
),
transforms.LULinear(parameter_dim, identity_init=True),
]
)
for i in range(flow_num_transforms)
]
)
transform = transforms.CompositeTransform([standardizing_transform, transform,])
distribution = distributions_.StandardNormal((parameter_dim,))
neural_net = flows.Flow(transform, distribution, embedding)
else:
raise ValueError
return neural_net
def build_made(
batch_x: Tensor,
batch_y: Tensor,
z_score_x: Optional[str] = "independent",
z_score_y: Optional[str] = "independent",
hidden_features: int = 50,
num_mixture_components: int = 10,
embedding_net: nn.Module = nn.Identity(),
**kwargs,
) -> nn.Module:
"""Builds MADE p(x|y).
Args:
batch_x: Batch of xs, used to infer dimensionality and (optional) z-scoring.
batch_y: Batch of ys, used to infer dimensionality and (optional) z-scoring.
z_score_x: Whether to z-score xs passing into the network, can be one of:
- `none`, or None: do not z-score.
- `independent`: z-score each dimension independently.
- `structured`: treat dimensions as related, therefore compute mean and std
over the entire batch, instead of per-dimension. Should be used when each
sample is, for example, a time series or an image.
z_score_y: Whether to z-score ys passing into the network, same options as
z_score_x.
hidden_features: Number of hidden features.
num_mixture_components: Number of mixture components.
embedding_net: Optional embedding network for y.
kwargs: Additional arguments that are passed by the build function but are not
relevant for mades and are therefore ignored.
Returns:
Neural network.
"""
x_numel = batch_x[0].numel()
# Infer the output dimensionality of the embedding_net by making a forward pass.
check_data_device(batch_x, batch_y)
check_embedding_net_device(embedding_net=embedding_net, datum=batch_y)
y_numel = embedding_net(batch_y[:1]).numel()
if x_numel == 1:
warn(
"In one-dimensional output space, this flow is limited to Gaussians"
)
transform = transforms.IdentityTransform()
z_score_x_bool, structured_x = z_score_parser(z_score_x)
if z_score_x_bool:
transform_zx = standardizing_transform(batch_x, structured_x)
transform = transforms.CompositeTransform([transform_zx, transform])
z_score_y_bool, structured_y = z_score_parser(z_score_y)
if z_score_y_bool:
embedding_net = nn.Sequential(standardizing_net(batch_y, structured_y),
embedding_net)
distribution = distributions_.MADEMoG(
features=x_numel,
hidden_features=hidden_features,
context_features=y_numel,
num_blocks=5,
num_mixture_components=num_mixture_components,
use_residual_blocks=True,
random_mask=False,
activation=relu,
dropout_probability=0.0,
use_batch_norm=False,
custom_initialization=True,
)
neural_net = flows.Flow(transform, distribution, embedding_net)
return neural_net
